Artificial Intelligence Medical Compendium

Explore the latest research on artificial intelligence and machine learning in medicine.

Showing 53,681 to 53,690 of 225,930 articles

M3: High-fidelity Text-to-Image Generation via Multi-Modal, Multi-Agent and Multi-Round Visual Reasoning

arXiv Feb 5, 2026
Generative models have achieved impressive fidelity in text-to-image synthesis, yet struggle with complex compositional prompts involving multiple constraints. We introduce \textbf{M3 (Multi-Modal, Multi-Agent, Multi-Round)}, a training-free framewor... read more 
Computer Vision and Pattern Recognition

Know Your Scientist: KYC as Biosecurity Infrastructure

arXiv Feb 5, 2026
Biological AI tools for protein design and structure prediction are advancing rapidly, creating dual-use risks that existing safeguards cannot adequately address. Current model-level restrictions, including keyword filtering, output screening, and co... read more 
Cryptography and Security cs.CY cs.LG

Unsupervised Anomaly Detection of Diseases in the Female Pelvis for Real-Time MR Imaging

arXiv Feb 5, 2026
Pelvic diseases in women of reproductive age represent a major global health burden, with diagnosis frequently delayed due to high anatomical variability, complicating MRI interpretation. Existing AI approaches are largely disease-specific and lack r... read more 
Computer Vision and Pattern Recognition

PhenoLIP: Integrating Phenotype Ontology Knowledge into Medical Vision-Language Pretraining

arXiv Feb 5, 2026
Recent progress in large-scale CLIP-like vision-language models(VLMs) has greatly advanced medical image analysis. However, most existing medical VLMs still rely on coarse image-text contrastive objectives and fail to capture the systematic visual kn... read more 
Computer Vision and Pattern Recognition cs.CL

AnyThermal: Towards Learning Universal Representations for Thermal Perception

arXiv Feb 5, 2026
We present AnyThermal, a thermal backbone that captures robust task-agnostic thermal features suitable for a variety of tasks such as cross-modal place recognition, thermal segmentation, and monocular depth estimation using thermal images. Existing t... read more 
Computer Vision and Pattern Recognition cs.AI cs.LG cs.RO

Learning Rate Scaling across LoRA Ranks and Transfer to Full Finetuning

arXiv Feb 5, 2026
Low-Rank Adaptation (LoRA) is a standard tool for parameter-efficient finetuning of large models. While it induces a small memory footprint, its training dynamics can be surprisingly complex as they depend on several hyperparameters such as initializ... read more 
Machine Learning cs.AI cs.CL

DroneKey++: A Size Prior-free Method and New Benchmark for Drone 3D Pose Estimation from Sequential Images

arXiv Feb 5, 2026
Accurate 3D pose estimation of drones is essential for security and surveillance systems. However, existing methods often rely on prior drone information such as physical sizes or 3D meshes. At the same time, current datasets are small-scale, limited... read more 
Computer Vision and Pattern Recognition

Cross-Modal Redundancy and the Geometry of Vision-Language Embeddings

arXiv Feb 5, 2026
Vision-language models (VLMs) align images and text with remarkable success, yet the geometry of their shared embedding space remains poorly understood. To probe this geometry, we begin from the Iso-Energy Assumption, which exploits cross-modal redun... read more 
Computer Vision and Pattern Recognition cs.LG

Inheritance Between Feedforward and Convolutional Networks via Model Projection

arXiv Feb 5, 2026
Techniques for feedforward networks (FFNs) and convolutional networks (CNNs) are frequently reused across families, but the relationship between the underlying model classes is rarely made explicit. We introduce a unified node-level formalization wit... read more 
Machine Learning cs.LG

GRP-Obliteration: Unaligning LLMs With a Single Unlabeled Prompt

arXiv Feb 5, 2026
Safety alignment is only as robust as its weakest failure mode. Despite extensive work on safety post-training, it has been shown that models can be readily unaligned through post-deployment fine-tuning. However, these methods often require extensive... read more 
Machine Learning cs.AI
Popular Topics
Recent Journals